Description: 语音增强利用最小均方误差短时谱幅度估计，英文文献，很好的外文资料。-Speech enhancement using MMSE short time spectral amplitude estimation, English literature, foreign language, good information. Platform: |
Size: 184320 |
Author:童话 |
Hits:
Description: 语音增强是影响语音识别系统性能的重要成分。为了比较语音增强算法的性能，采用Matlab软件进行了数值仿真，对不同噪声环境下的语音用3种不同的方法进行降噪，采用信噪比、端点检测等方法来降噪效果，并对几种增强算法的性能进行了比较分析。结果表明，在变噪声环境下短时谱MMSE法最佳，谱减法和维纳滤波法各有优点。-Speech enhancement of voice recognition is an important component of system performance. In order to compare the performance of speech enhancement algorithm using the Matlab software, a numerical simulation, speech under different noise environments with 3 different methods of noise reduction, the use of signal to noise ratio, endpoint detection method to the noise reduction effect, and a few kinds of enhanced performance of the algorithm were compared. The results show that changing the noise environment in the MMSE method was the best short-term spectrum, spectral subtraction and Wiener filtering methods have their advantages. Platform: |
Size: 376832 |
Author:static |
Hits:
Description: 传统的短时谱估计语音增强算法通常假设语音谱分量相互独立，没有考虑语音谱分量间的相关性。针对这
一问题，该文提出一种新的基于多元Laplace分布模型的短时谱估计算法。首先，假设语音的离散余弦变换(DCT)
系数服从多元Laplace分布，以此利用谱分量间的相关性；在此基础上，利用多元随机矢量的高斯尺度混合模型表
示，推导得到语音DCT系数矢量的最小均方误差(MMSE)估计的解析表达式；并进一步推导了基于该分布模型的
语音存在概率，对最小均方误差估计子进行修正。实验结果表明，该算法在抑制背景噪声和减少语音失真等方面优
于传统的语音增强方法。-The spectral components of speech are usually assumed to be independent in traditional short-time
spectrum estimation, which is not the case in practice. Tosolve this problem, a new speech enhancement algorithm
with multivariate Laplace speech model is proposed in this paper. Firstly, the speech Discrete Cosine Transform
(DCT) coefficients are modeled by a multivariate Laplace distribution, so the correlations between speech spectral
components can be exploited. And then a Minimum-Mean-Square-Error (MMSE) estimator based on the proposed
model is derived using a Gaussian scale mixture representation of random vectors. Furthermore, the speech
presence uncertainty with the new model is derived to modify the MMSE estimator. Experimental results show
that the developed method has better noise suppression performance and lower speech distortion compared to the
traditional speech enhancement method. Platform: |
Size: 1054720 |
Author:立枣酒 |
Hits:
Search - speech enhancement using mmse